{"id":"https://openalex.org/W2109772895","doi":"https://doi.org/10.3115/1218955.1218963","title":"Statistical modeling for unit selection in speech synthesis","display_name":"Statistical modeling for unit selection in speech synthesis","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2109772895","doi":"https://doi.org/10.3115/1218955.1218963","mag":"2109772895"},"language":"en","primary_location":{"id":"doi:10.3115/1218955.1218963","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1218963","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1218963","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1218963","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030888546","display_name":"Cyril Allauzen","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cyril Allauzen","raw_affiliation_strings":["AT&T Labs -- Research, Florham Park, NJ","AT&T Labs\u2014\u2014Research, Florham Park, NJ#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs -- Research, Florham Park, NJ","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Labs\u2014\u2014Research, Florham Park, NJ#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058849006","display_name":"Mehryar Mohri","orcid":"https://orcid.org/0000-0002-3987-9847"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehryar Mohri","raw_affiliation_strings":["AT&T Labs -- Research, Florham Park, NJ","AT&T Labs\u2014\u2014Research, Florham Park, NJ#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs -- Research, Florham Park, NJ","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Labs\u2014\u2014Research, Florham Park, NJ#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014137885","display_name":"Michael Riley","orcid":"https://orcid.org/0009-0002-9449-025X"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Riley","raw_affiliation_strings":["AT&T Labs -- Research, Florham Park, NJ","AT&T Labs\u2014\u2014Research, Florham Park, NJ#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs -- Research, Florham Park, NJ","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Labs\u2014\u2014Research, Florham Park, NJ#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"55","last_page":"es"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.8709708452224731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7978967428207397},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6058858036994934},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5504664778709412},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5474553108215332},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.5027310848236084},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.4728142321109772},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4361097812652588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42545977234840393},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.4241524934768677},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.4217085838317871},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3270866274833679},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09971487522125244}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.8709708452224731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7978967428207397},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6058858036994934},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5504664778709412},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5474553108215332},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5027310848236084},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.4728142321109772},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4361097812652588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42545977234840393},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.4241524934768677},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.4217085838317871},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3270866274833679},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09971487522125244},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/1218955.1218963","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1218963","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1218963","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.3.9490","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.9490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/~allauzen/./pdf/usel.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.4.3762","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.3762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/~allauzen/postscript/usel.ps","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1218955.1218963","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1218963","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1218963","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2109772895.pdf","grobid_xml":"https://content.openalex.org/works/W2109772895.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W27049869","https://openalex.org/W36566811","https://openalex.org/W67398698","https://openalex.org/W71082305","https://openalex.org/W108392250","https://openalex.org/W245263649","https://openalex.org/W1505482284","https://openalex.org/W1578332044","https://openalex.org/W1595816827","https://openalex.org/W1607161872","https://openalex.org/W1625762979","https://openalex.org/W1797288984","https://openalex.org/W1860547055","https://openalex.org/W1903115690","https://openalex.org/W1990005915","https://openalex.org/W2087382212","https://openalex.org/W2125528794","https://openalex.org/W2130629108","https://openalex.org/W2134237567","https://openalex.org/W2150658333","https://openalex.org/W2167954650","https://openalex.org/W2394962911","https://openalex.org/W2428180336","https://openalex.org/W4302312245"],"related_works":["https://openalex.org/W234770729","https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W2387179309","https://openalex.org/W3094724019","https://openalex.org/W2388979876","https://openalex.org/W4245668640","https://openalex.org/W2032960563","https://openalex.org/W2142993035","https://openalex.org/W2899044948"],"abstract_inverted_index":{"Traditional":[0],"concatenative":[1],"speech":[2,44,69],"synthesis":[3],"systems":[4],"use":[5,103,163,204],"a":[6,33,57,68,76,80,86,112,131,155],"number":[7],"of":[8,21,67,100,114,147,150,164,187,207],"heuristics":[9],"to":[10,28,75,110,177],"define":[11],"the":[12,19,22,64,97,120,145,148,151,184,188,195,203],"target":[13],"and":[14,79,142,153,157,198,205,209],"concatenation":[15,121],"costs,":[16],"essential":[17],"for":[18,38,144,167,202],"design":[20],"unit":[23,39,60,88,107,115,173],"selection":[24,40,89,108,174],"component.":[25],"In":[26],"contrast":[27],"these":[29],"approaches,":[30],"we":[31,102],"introduce":[32],"general":[34,65],"statistical":[35,93,132,172],"modeling":[36],"framework":[37,53],"inspired":[41],"by":[42],"automatic":[43],"recognition.":[45],"Given":[46],"appropriate":[47],"data,":[48,101],"techniques":[49],"based":[50,91],"on":[51,92],"that":[52,119],"can":[54,72,123],"result":[55],"in":[56],"more":[58,77,82,158,210],"accurate":[59],"selection,":[61],"thereby":[62],"improving":[63],"quality":[66],"synthesizer.":[70],"They":[71],"also":[73],"lead":[74],"modular":[78],"substantially":[81],"efficient":[83,159],"system.We":[84],"present":[85],"new":[87,156,208],"system":[90,109,152],"modeling.":[94],"To":[95],"overcome":[96],"original":[98],"absence":[99],"an":[104],"existing":[105],"high-quality":[106],"generate":[111],"corpus":[113,129],"sequences.":[116],"We":[117,138],"show":[118],"cost":[122],"be":[124,178],"accurately":[125],"estimated":[126],"from":[127],"this":[128],"using":[130],"n-gram":[133],"language":[134],"model":[135],"over":[136],"units.":[137],"used":[139],"weighted":[140],"automata":[141],"transducers":[143],"representation":[146],"components":[149],"designed":[154],"composition":[160],"algorithm":[161],"making":[162],"string":[165],"potentials":[166],"their":[168],"combination.":[169],"The":[170],"resulting":[171],"is":[175],"shown":[176],"about":[179],"2.6":[180],"times":[181],"faster":[182],"than":[183],"last":[185],"release":[186],"AT&T":[189],"Natural":[190],"Voices":[191],"Product":[192],"while":[193],"preserving":[194],"same":[196],"quality,":[197],"offers":[199],"much":[200],"flexibility":[201],"integration":[206],"complex":[211],"components.":[212]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}